SOTAVerified

HellaSwag

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–39 of 39 papers

TitleStatusHype
Training Compute-Optimal Large Language ModelsCode6
LayerSkip: Enabling Early Exit Inference and Self-Speculative DecodingCode3
DataDecide: How to Predict Best Pretraining Data with Small ExperimentsCode3
Scaling Language Models: Methods, Analysis & Insights from Training GopherCode2
UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask BenchmarkCode1
When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data AugmentationCode1
An Open Source Data Contamination Report for Large Language ModelsCode1
Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language ModelsCode1
LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA OptimizationCode1
More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment—0
Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models—0
Elastic Weight Consolidation for Full-Parameter Continual Pre-Training of Gemma2—0
Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning—0
Teuken-7B-Base & Teuken-7B-Instruct: Towards European LLMs—0
Promises, Outlooks and Challenges of Diffusion Language Modeling—0
English Intermediate-Task Training Improves Zero-Shot Cross-Lingual Transfer Too—0
Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst—0
Slimming Down LLMs Without Losing Their Minds—0
Comparing Test Sets with Item Response Theory—0
SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs—0
Contrastive Decoding Improves Reasoning in Large Language Models—0
Towards Multilingual LLM Evaluation for European Languages—0
GRIN: GRadient-INformed MoE—0
When Chosen Wisely, More Data Is What You Need: A Universal Sample-Efficient Strategy For Data Augmentation—0
Who's Harry Potter? Approximate Unlearning in LLMs—0
HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning—0
Domain-Adaptive Continued Pre-Training of Small Language Models—0
You can remove GPT2's LayerNorm by fine-tuningCode0
Attacks on Node Attributes in Graph Neural NetworksCode0
FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level FilteringCode0
GraDA: Graph Generative Data Augmentation for Commonsense ReasoningCode0
HellaSwag: Can a Machine Really Finish Your Sentence?Code0
In-Contextual Gender Bias Suppression for Large Language ModelsCode0
On Curriculum Learning for Commonsense ReasoningCode0
SaGE: Evaluating Moral Consistency in Large Language ModelsCode0
Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM EvaluationCode0
metabench -- A Sparse Benchmark to Measure General Ability in Large Language ModelsCode0
Toward Adversarial Training on Contextualized Language RepresentationCode0
What the HellaSwag? On the Validity of Common-Sense Reasoning BenchmarksCode0
Show:102550

No leaderboard results yet.